From ceb94d3173d905b5e1778a996e70bdca5c0f6a08 Mon Sep 17 00:00:00 2001
From: zachary62 <zhuang333@wisc.edu>
Date: Sun, 29 Dec 2024 20:41:14 +0000
Subject: [PATCH] tool

---
 docs/batch.md |   2 +-
 docs/index.md |   2 +-
 docs/llm.md   |   4 +-
 docs/tool.md  | 165 ++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 169 insertions(+), 4 deletions(-)
 create mode 100644 docs/tool.md

diff --git a/docs/batch.md b/docs/batch.md
index 9396d1f..24cafb0 100644
--- a/docs/batch.md
+++ b/docs/batch.md
@@ -71,7 +71,7 @@ summarize_all_files = SummarizeAllFiles(start=summarize_file)
 summarize_all_files.run(shared)
 ```
 
-**Under the Hood**:
+### Under the Hood
 1. `prep(shared)` returns a list of param dicts—e.g., `[{filename: "file1.txt"}, {filename: "file2.txt"}, ...]`.
 2. The **BatchFlow** loops through each dict. For each one:
    - It merges the dict with the BatchFlow’s own `params`.
diff --git a/docs/index.md b/docs/index.md
index 7d2bcc4..72b517d 100644
--- a/docs/index.md
+++ b/docs/index.md
@@ -30,7 +30,7 @@ We model the LLM workflow as a **Nested Flow**:
 
 ## Preparation
 
-- [LLM Integration](./llm.md)
+- [LLM Wrapper](./llm.md)
 - Tools
 
 ## Paradigm Implementation
diff --git a/docs/llm.md b/docs/llm.md
index e1612a9..9229940 100644
--- a/docs/llm.md
+++ b/docs/llm.md
@@ -1,13 +1,13 @@
 ---
 layout: default
-title: "LLM Integration"
+title: "LLM Wrapper"
 parent: "Preparation"
 nav_order: 1
 ---
 
 # LLM Wrappers  
 
-We **don't** provide built-in wrapper LLM wrappers. Instead, please implement your own, for example by asking an assistant like ChatGPT or Claude. If you ask ChatGPT to "implement a `call_llm` function that takes a prompt and returns the LLM response," you shall get something like:
+We **don't** provide built-in LLM wrappers. Instead, please implement your own, for example by asking an assistant like ChatGPT or Claude. If you ask ChatGPT to "implement a `call_llm` function that takes a prompt and returns the LLM response," you shall get something like:
 
 ```python
 def call_llm(prompt):
diff --git a/docs/tool.md b/docs/tool.md
new file mode 100644
index 0000000..a0256b0
--- /dev/null
+++ b/docs/tool.md
@@ -0,0 +1,165 @@
+---
+layout: default
+title: "Tool"
+parent: "Preparation"
+nav_order: 2
+---
+
+# Tool
+
+Similar to LLM wrappers, we **don't** provide built-in tools. Here, we recommend some *minimal* (and incomplete) implementations of commonly used tools. These examples can serve as a starting point for your own tooling.
+
+---
+
+
+## 1. Embedding Calls
+
+```python
+def get_embedding(text):
+    import openai
+    # Set your API key elsewhere, e.g., environment variables
+    r = openai.Embedding.create(
+        model="text-embedding-ada-002",
+        input=text
+    )
+    return r["data"][0]["embedding"]
+```
+
+---
+
+## 2. Vector Database (Faiss)
+
+```python
+import faiss
+import numpy as np
+
+def create_index(embeddings):
+    dim = len(embeddings[0])
+    index = faiss.IndexFlatL2(dim)
+    index.add(np.array(embeddings).astype('float32'))
+    return index
+
+def search_index(index, query_embedding, top_k=5):
+    D, I = index.search(
+        np.array([query_embedding]).astype('float32'), 
+        top_k
+    )
+    return I, D
+```
+
+---
+
+## 3. Local Database
+
+```python
+import sqlite3
+
+def execute_sql(query):
+    conn = sqlite3.connect("mydb.db")
+    cursor = conn.cursor()
+    cursor.execute(query)
+    result = cursor.fetchall()
+    conn.commit()
+    conn.close()
+    return result
+```
+
+---
+
+## 4. Python Function Execution
+
+```python
+def run_code(code_str):
+    env = {}
+    exec(code_str, env)
+    return env
+```
+
+---
+
+## 5. PDF Extraction
+
+```python
+def extract_text_from_pdf(file_path):
+    import PyPDF2
+    pdfFileObj = open(file_path, "rb")
+    reader = PyPDF2.PdfReader(pdfFileObj)
+    text = ""
+    for page in reader.pages:
+        text += page.extract_text()
+    pdfFileObj.close()
+    return text
+```
+
+---
+
+## 6. Web Crawling
+
+```python
+def crawl_web(url):
+    import requests
+    from bs4 import BeautifulSoup
+    html = requests.get(url).text
+    soup = BeautifulSoup(html, "html.parser")
+    return soup.title.string, soup.get_text()
+```
+
+---
+
+## 7. Basic Search (SerpAPI example)
+
+```python
+def search_google(query):
+    import requests
+    params = {
+        "engine": "google",
+        "q": query,
+        "api_key": "YOUR_API_KEY"
+    }
+    r = requests.get("https://serpapi.com/search", params=params)
+    return r.json()
+```
+
+---
+
+
+## 8. Audio Transcription (OpenAI Whisper)
+
+```python
+def transcribe_audio(file_path):
+    import openai
+    audio_file = open(file_path, "rb")
+    transcript = openai.Audio.transcribe("whisper-1", audio_file)
+    return transcript["text"]
+```
+
+---
+
+## 9. Text-to-Speech (TTS)
+
+```python
+def text_to_speech(text):
+    import pyttsx3
+    engine = pyttsx3.init()
+    engine.say(text)
+    engine.runAndWait()
+```
+
+---
+
+## 10. Sending Email
+
+```python
+def send_email(to_address, subject, body, from_address, password):
+    import smtplib
+    from email.mime.text import MIMEText
+
+    msg = MIMEText(body)
+    msg["Subject"] = subject
+    msg["From"] = from_address
+    msg["To"] = to_address
+
+    with smtplib.SMTP_SSL("smtp.gmail.com", 465) as server:
+        server.login(from_address, password)
+        server.sendmail(from_address, [to_address], msg.as_string())
+```
\ No newline at end of file